Automated Alerts for Heart Valve Issues

(ALERT Trial)

Recruiting at 5 trial locations

Overseen By Loren Wagner, PhD

Age: 18+

Sex: Any

Travel: May Be Covered

Time Reimbursement: Varies

Trial Phase: Academic

Recruiting

Sponsor: Tempus Labs

Disqualifiers: Age < 18, Prior valve repair, others

No Placebo Group

Approved in 1 Jurisdiction

Trial Summary

What is the purpose of this trial?

This multi-center, prospective, cluster-randomized controlled trial will evaluate Tempus Next automated notifications as an intervention to support identification and evaluation of patients possibly indicated for Valve Intervention (VI). This study will evaluate the impact of Tempus Next's automated notifications on: (1) Transcatheter or surgical procedure for AS or MR; and (2) Clinic visit with at least one member of the Multidisciplinary Heart Team (including time to evaluation) for patients with definitive or possible severe AS or MR on echocardiogram. These endpoints will also be examined within and between assigned groups according to race, ethnicity, sex, and geography. The primary question that will be answered: Do automated alerts sent to clinical providers decrease under-treatment of severe aortic stenosis and severe mitral regurgitation? The study will compare the rate of clinical follow-up and aortic valve surgery in a control group (no alerts sent) to a treatment group (alerts sent to an appropriate care provider).

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial coordinators or your doctor.

What data supports the effectiveness of the treatment Automated alert, Tempus Next Automated Notifications, EHR Notifications for heart valve issues?

Research shows that automated alert systems can effectively notify doctors about serious health conditions, leading to quick responses and actions. In one study, doctors responded to over 70% of alerts, often within 15 minutes, and took action in many cases, suggesting these systems can improve healthcare management. ^{1 2 3 4 5}

Is the Automated Alerts for Heart Valve Issues treatment safe for humans?

The research articles do not provide specific safety data for the Automated Alerts for Heart Valve Issues treatment, but they discuss the use of automated alerts in healthcare settings, which are generally used to improve clinical responses and prevent adverse events. ^{3 4 5 6 7}

How is the Automated alert treatment for heart valve issues different from other treatments?

The Automated alert treatment is unique because it uses electronic health record (EHR) notifications to automatically alert clinicians about heart valve issues, allowing for timely intervention. Unlike traditional treatments that may rely on periodic check-ups or patient-reported symptoms, this system provides real-time alerts, potentially improving response times and outcomes. ^{3 4 5 8 9}

Research Team

Wayne Batchelor, MD

Principal Investigator

Director of Interventional Cardiology Inova Heart and Vascular Institute

Eligibility Criteria

This trial is for patients with severe aortic stenosis (AS) or mitral regurgitation (MR), as indicated by specific measurements on an echocardiogram. It's not for those who don't meet the required echo criteria, such as AVA ≤ 1.0 cm2 or Dimensionless index ≤ 0.25 for AS, and certain criteria for MR.

Inclusion Criteria

My heart's aortic valve area or Doppler velocity index was measured.

My heart's aortic valve area and another echo measurement have been checked.

My heart valve area is 1.2 cm2 or less.

Trial Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Automated alerts are sent to clinical providers to support identification and evaluation of patients for Valve Intervention (VI)

90 days

Ongoing monitoring through EHR

Follow-up

Participants are monitored for the impact of automated alerts on clinical follow-up and valve intervention rates

4 weeks

Treatment Details

Interventions

• Automated alert (Behavioral Intervention)

Trial Overview The study tests if automated alerts to doctors can reduce under-treatment of severe AS and MR by comparing follow-up rates and valve surgeries between two groups: one receiving alerts and one not.

Participant Groups

Group I: Automated alert Experimental Treatment 1 Intervention

Providers that will receive an automated alert sent via the EHR.

Group II: Control Active Control 1 Intervention

Care providers in the control arm will not receive an automated alert.

Who Is Running the Clinical Trial?

Tempus Labs

Lead Sponsor

Trials

17

Recruited

20,200+

Tempus AI

Lead Sponsor

Trials

18

Recruited

20,700+

Medtronic

Industry Sponsor

Trials

627

Recruited

767,000+

Geoff Martha

Medtronic

Chief Executive Officer since 2020

Finance degree from Penn State University

Dr. Richard Kuntz

Medtronic

Chief Medical Officer since 2023

MD, MSc

Findings from Research

A new alert system for inpatients successfully notified physicians about serious clinical conditions, with a high response rate of 70.2% to 1730 alerts over a 6-month period.

Physicians acted quickly, responding to 82.5% of alerts within 15 minutes, and indicated they would take action in 71.5% of cases, suggesting the system is effective in facilitating timely medical responses.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Detecting alerts, notifying the physician, and offering action items: a comprehensive alerting system. Kuperman, GJ., Teich, JM., Bates, DW., et al.[2018]

Automated alerts and reminders for patients can significantly improve adherence to healthcare regimens, as shown in a review of 51 studies, indicating their effectiveness in fostering shared accountability for health outcomes.

These reminders can be personalized and are effective across various age groups, suggesting that as technology advances, their use will likely expand, leading to better patient management and potentially lower healthcare costs.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Automated alerts and reminders targeting patients: A review of the literature. Perri-Moore, S., Kapsandoy, S., Doyon, K., et al.[2022]

Primary care practitioners (PCPs) received an average of 56.4 asynchronous electronic health record (EHR) alerts per day, which significantly contributes to their workload.

On average, PCPs spent about 49 minutes each day processing these alerts, highlighting the need for further investigation into the effectiveness and management of such alert systems.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Notifications received by primary care practitioners in electronic health records: a taxonomy and time analysis. Murphy, DR., Reis, B., Sittig, DF., et al.[2022]

A survey of 30 medical centers revealed that 57% of them use electronic health record (EHR) alerts (e-alerts) for early detection of conditions like sepsis and pneumonia, indicating a proactive approach to patient safety in acute care settings.

Despite the widespread use of e-alerts, only 59% of the sites have assessed their accuracy or validity, highlighting a need for improved evaluation practices to ensure the effectiveness of these alerts in clinical decision-making.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The Nature and Variability of Automated Practice Alerts Derived from Electronic Health Records in a U.S. Nationwide Critical Care Research Network. Benthin, C., Pannu, S., Khan, A., et al.[2020]

A new clinical alerting system has been developed to monitor laboratory results for both hospitalized and ambulatory patients in Israel, aiming to improve clinician response to critical results.

This system allows for customizable alerts based on individual clinician preferences and critical thresholds, enhancing its versatility and potential effectiveness in various medical settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A comprehensive computerized critical laboratory results alerting system for ambulatory and hospitalized patients. Iordache, SD., Orso, D., Zelingher, J.[2008]

In a study of 623 patients across ICU and general ward settings, automated trigger alerts for drug-related hazardous conditions (DRHCs) were found to be clinically significant in about 89% of cases in the ICU and 83% in general wards, indicating their effectiveness in both environments.

The positive predictive value (PPV) for alerts identifying DRHCs was 0.66 in the ICU and 0.76 in general wards, suggesting that while alerts are beneficial, there is room for improvement in their performance across both patient care settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Evaluation of an automated surveillance system using trigger alerts to prevent adverse drug events in the intensive care unit and general ward. DiPoto, JP., Buckley, MS., Kane-Gill, SL.[2022]

In a study analyzing 1012 medication regimens in a nephrology clinic, more specific alerting strategies significantly reduced the number of alerts generated, with the most advanced strategy (D) resulting in alerts for only 7.81% of regimens compared to 87.5% with the least specific strategy (A).

The findings suggest that using patient and drug-specific information in alert systems can effectively minimize alert fatigue among physicians, potentially improving the safety of prescribing medications to patients with renal impairment.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Tailoring of alerts substantially reduces the alert burden in computerized clinical decision support for drugs that should be avoided in patients with renal disease. Czock, D., Konias, M., Seidling, HM., et al.[2017]

The study presents an automated approach to managing communication modalities for event monitors, which simplifies the customization process for users and institutions, making it easier to handle multiple clinical conditions.

By using generic notification attributes and criteria, the system allows for more efficient assignment of alerts that are independent of specific clinical conditions, enhancing the reusability and sharability of the event monitor's knowledge base.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Extended attributes of event monitor systems for criteria-based notification modalities. Tao, Y., Wang, D., Shortliffe, EH., et al.[2018]

A study analyzing interruptive alerts in electronic health records across 6 pediatric health systems from 2016-2019 found significant variation in alert burden, with custom alerts being the most frequent across all sites.

The choice of metric used to measure alert burden (such as alerts per patient encounter or alerts per clinician day) greatly influenced which provider types and care settings were identified as having the highest alert burden, highlighting the importance of metric selection in evaluating EHR alert systems.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Alert burden in pediatric hospitals: a cross-sectional analysis of six academic pediatric health systems using novel metrics. Orenstein, EW., Kandaswamy, S., Muthu, N., et al.[2022]

References

1. United States pubmed.ncbi.nlm.nih.gov

Detecting alerts, notifying the physician, and offering action items: a comprehensive alerting system. [2018]

2. Ireland pubmed.ncbi.nlm.nih.gov

Automated alerts and reminders targeting patients: A review of the literature. [2022]

3. United States pubmed.ncbi.nlm.nih.gov

Notifications received by primary care practitioners in electronic health records: a taxonomy and time analysis. [2022]

4. United States pubmed.ncbi.nlm.nih.gov

The Nature and Variability of Automated Practice Alerts Derived from Electronic Health Records in a U.S. Nationwide Critical Care Research Network. [2020]

5. Netherlands pubmed.ncbi.nlm.nih.gov

A comprehensive computerized critical laboratory results alerting system for ambulatory and hospitalized patients. [2008]

6. New Zealand pubmed.ncbi.nlm.nih.gov

Evaluation of an automated surveillance system using trigger alerts to prevent adverse drug events in the intensive care unit and general ward. [2022]

7. England pubmed.ncbi.nlm.nih.gov

Tailoring of alerts substantially reduces the alert burden in computerized clinical decision support for drugs that should be avoided in patients with renal disease. [2017]

8. United States pubmed.ncbi.nlm.nih.gov

Extended attributes of event monitor systems for criteria-based notification modalities. [2018]

9. England pubmed.ncbi.nlm.nih.gov

Alert burden in pediatric hospitals: a cross-sectional analysis of six academic pediatric health systems using novel metrics. [2022]